New in 0.20.0 (2023-02-01)#
Major changes#
Model hyperparameter tuning is available through
ModelTuner
(beta) #1785,#1802,#1831.Pre-trained models can now be uploaded to and downloaded from Hugging Face models using the
hub
module #1779,#1812,#1828,#1841, #1851,#1862.AnnData
.var
and.varm
attributes can now be registered through new fields infields
#1830,#1839.SCBASSET
, a reimplementation of the original scBasset model, is available for representation learning of scATAC-seq data (experimental) #1839,#1844#1867,#1874,#1882.LowLevelPyroTrainingPlan
andPyroModelGuideWarmup
added to allow the use of vanilla PyTorch optimization on Pyro models #1845,#1847.Add
scvi.data.cellxgene()
function to download cellxgene datasets #1880.
Minor changes#
Latent mode support changed so that user data is no longer edited in-place #1756.
Minimum supported PyTorch Lightning version is now 1.9 #1795,#1833,#1863.
Minimum supported Python version is now 3.8 #1819.
Poetry removed in favor of Hatch for builds and publishing #1823.
setup_anndata
docstrings fixed,setup_mudata
docstrings added #1834,#1837.add_dna_sequence()
adds DNA sequences toAnnData
objects using genomepy #1839,#1842.Update tutorial formatting with pre-commit #1850
Development in GitHub Codespaces is now supported #1836.
Breaking changes#
LossRecorder
has been removed in favor ofLossOutput
#1869.
Bug Fixes#
JaxTrainingPlan
now correctly updatesglobal_step
through PyTorch Lightning by using a dummy optimizer. #1791.Device-backed
AnnTorchDataset
fixed to work with sparse data #1824.Fix bug
compute_reconstruction_error()
causing the first batch to be ignored, see more details in #1854 #1857.